mirror of
https://github.com/langchain-ai/langchain.git
synced 2026-10-06 09:55:21 +03:00
Harrison ChaseandShreya Rajpal
985496f4be
Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2.5 KiB
2.5 KiB
In [1]:
from langchain.chains import LLMCheckerChain
from langchain.llms import OpenAI
llm = OpenAI(temperature=0.7)
text = "What type of mammal lays the biggest eggs?"
checker_chain = LLMCheckerChain(llm=llm, verbose=True)
checker_chain.run(text)Out [1]:
[1m> Entering new LLMCheckerChain chain...[0m
[1m> Entering new SequentialChain chain...[0m
[1mChain 0[0m:
{'statement': '\nNone. Mammals do not lay eggs.'}
[1mChain 1[0m:
{'assertions': '\n• Mammals reproduce using live birth\n• Mammals do not lay eggs\n• Animals that lay eggs are not mammals'}
[1mChain 2[0m:
{'checked_assertions': '\n1. True\n\n2. True\n\n3. False - Mammals are a class of animals that includes animals that lay eggs, such as monotremes (platypus and echidna).'}
[1mChain 3[0m:
{'revised_statement': ' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'}
[1m> Finished SequentialChain chain.[0m
[1m> Finished LLMCheckerChain chain.[0m
' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'
In [ ]: